Instructions to use wesjos/Spark-x2.6-4B-HTML with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use wesjos/Spark-x2.6-4B-HTML with Transformers:

# Use a pipeline as a high-level helper
from transformers import pipeline

pipe = pipeline("text-generation", model="wesjos/Spark-x2.6-4B-HTML", trust_remote_code=True)
messages = [
    {"role": "user", "content": "Who are you?"},
]
pipe(messages)

# pip install -U transformers accelerate
# Load model directly
from transformers import AutoModelForCausalLM
model = AutoModelForCausalLM.from_pretrained("wesjos/Spark-x2.6-4B-HTML", trust_remote_code=True, device_map="auto")

Notebooks
Google Colab
Kaggle
Local Apps Settings

vLLM

How to use wesjos/Spark-x2.6-4B-HTML with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "wesjos/Spark-x2.6-4B-HTML"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "wesjos/Spark-x2.6-4B-HTML",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/wesjos/Spark-x2.6-4B-HTML

SGLang

How to use wesjos/Spark-x2.6-4B-HTML with SGLang:

Install from pip and serve model

# Install SGLang from pip:
pip install sglang
# Start the SGLang server:
python3 -m sglang.launch_server \
    --model-path "wesjos/Spark-x2.6-4B-HTML" \
    --host 0.0.0.0 \
    --port 30000
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:30000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "wesjos/Spark-x2.6-4B-HTML",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker images

docker run --gpus all \
    --shm-size 32g \
    -p 30000:30000 \
    -v ~/.cache/huggingface:/root/.cache/huggingface \
    --env "HF_TOKEN=<secret>" \
    --ipc=host \
    lmsysorg/sglang:latest \
    python3 -m sglang.launch_server \
        --model-path "wesjos/Spark-x2.6-4B-HTML" \
        --host 0.0.0.0 \
        --port 30000
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:30000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "wesjos/Spark-x2.6-4B-HTML",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Docker Model Runner
How to use wesjos/Spark-x2.6-4B-HTML with Docker Model Runner:
```
docker model run hf.co/wesjos/Spark-x2.6-4B-HTML
```

Spark-x2.6-4B-HTML / webui /config.json

wesjos

update: wesjos/Spark-x2.6-4B-HTML

203de2a verified 10 days ago

Raw History Blame Contribute Delete

1.2 kB

{
  "backend_mode": "api",
  "api_url": "http://127.0.0.1:18080",
  "model_path": "/mnt/sdb/models/Spark-x2.6-4B-HTML/Spark-x2.6-4B-HTML-Q8_0.gguf",
  "model_alias": "Spark-x2.6-4B-HTML",
  "context_size": 131072,
  "gpu_layers": 99,
  "do_sample": true,
  "temperature": 0.7,
  "top_p": 0.8,
  "top_k": 40,
  "min_p": 0.05,
  "presence_penalty": 0.0,
  "repetition_penalty": 1.05,
  "max_tokens": 8192,
  "enable_thinking": true,
  "theme_preset": "notion",
  "custom_css": "/* Notion Minimal */\n.html-canvas {\n  border-radius: 4px !important;\n  border: 1px solid #37352f !important;\n  box-shadow: none !important;\n  background: #ffffff !important;\n}\n.card {\n  border-radius: 4px !important;\n  border: 1px solid #e3e2e0 !important;\n  box-shadow: none !important;\n}\n.summary-card {\n  border-radius: 4px !important;\n  border-left-color: #37352f !important;\n}\n.callout {\n  border-radius: 4px !important;\n  border-left-width: 4px !important;\n}\n.badge {\n  border-radius: 3px !important;\n  font-weight: 500 !important;\n}",
  "system_prompt": "You are Mario-html. You are a helpful assistant who generates nice visual content.",
  "reasoning_effort": "low",
  "frequency_penalty": 0.0
}

	{
	"backend_mode": "api",
	"api_url": "http://127.0.0.1:18080",
	"model_path": "/mnt/sdb/models/Spark-x2.6-4B-HTML/Spark-x2.6-4B-HTML-Q8_0.gguf",
	"model_alias": "Spark-x2.6-4B-HTML",
	"context_size": 131072,
	"gpu_layers": 99,
	"do_sample": true,
	"temperature": 0.7,
	"top_p": 0.8,
	"top_k": 40,
	"min_p": 0.05,
	"presence_penalty": 0.0,
	"repetition_penalty": 1.05,
	"max_tokens": 8192,
	"enable_thinking": true,
	"theme_preset": "notion",
	"custom_css": "/* Notion Minimal */\n.html-canvas {\n border-radius: 4px !important;\n border: 1px solid #37352f !important;\n box-shadow: none !important;\n background: #ffffff !important;\n}\n.card {\n border-radius: 4px !important;\n border: 1px solid #e3e2e0 !important;\n box-shadow: none !important;\n}\n.summary-card {\n border-radius: 4px !important;\n border-left-color: #37352f !important;\n}\n.callout {\n border-radius: 4px !important;\n border-left-width: 4px !important;\n}\n.badge {\n border-radius: 3px !important;\n font-weight: 500 !important;\n}",
	"system_prompt": "You are Mario-html. You are a helpful assistant who generates nice visual content.",
	"reasoning_effort": "low",
	"frequency_penalty": 0.0
	}